Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    beta cells

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	u
    -0.08
    훗
    -0.07
     ft
    -0.07
    פורסם
    -0.07
    :flutter
    -0.07
     tüm
    -0.07
     dice
    -0.07
    ihanna
    -0.07
     tremendous
    -0.07
     prostitu
    -0.07
    POSITIVE LOGITS
     Macro
    0.07
     Rib
    0.07
    هد
    0.07
    erval
    0.07
    :length
    0.07
    이며
    0.06
    ench
    0.06
    stro
    0.06
    궈
    0.06
    tória
    0.06
    Act Density 0.011%

    No Known Activations